Filters








224,707 Hits in 9.3 sec

Federated Learning: Challenges, Methods, and Future Directions [article]

Tian Li, Anit Kumar Sahu, Ameet Talwalkar, Virginia Smith
2019 arXiv   pre-print
In this article, we discuss the unique characteristics and challenges of federated learning, provide a broad overview of current approaches, and outline several directions of future work that are relevant  ...  Training in heterogeneous and potentially massive networks introduces novel challenges that require a fundamental departure from standard approaches for large-scale machine learning, distributed optimization  ...  We thank Jeffrey Li and Mikhail Khodak for helpful discussions and comments.  ... 
arXiv:1908.07873v1 fatcat:pcztnmhquvd65es6wdz34igbhi

Federated Learning for 6G Communications: Challenges, Methods, and Future Directions [article]

Yi Liu, Xingliang Yuan, Zehui Xiong, Jiawen Kang, Xiaofei Wang, Dusit Niyato
2020 arXiv   pre-print
We then describe key technical challenges, the corresponding federated learning methods, and open problems for future research on federated learning in the context of 6G communications.  ...  In this article, we first introduce the integration of 6G and federated learning and provide potential federated learning applications for 6G.  ...  OPEN RESEARCH TOPICS AND FUTURE DIRECTIONS A.  ... 
arXiv:2006.02931v2 fatcat:df3bzirq2fcpnp7h3kagdgamiy

A Survey of Deep Learning for Retinal Blood Vessel Segmentation Methods: Taxonomy, Trends, Challenges and Future Directions

Olubunmi Omobola Sule
2022 IEEE Access  
recent work, identify the challenges, and suggest potential future research directions.  ...  The taxonomies focused on in this paper include optimization algorithms, regularization methods, pooling operations, activation functions, transfer learning, and ensemble learning methods.  ...  TREND ANALYSIS, CHALLENGES, AND FUTURE DIRECTIONS To meet the set objectives, the trend analysis, challenges, suggestions, and future research directions are detailed in this section. A.  ... 
doi:10.1109/access.2022.3163247 fatcat:26cg6qemhzagvhjdhbv37dm46i

6G-enabled Edge AI for Metaverse: Challenges, Methods, and Future Research Directions [article]

Luyi Chang, Zhe Zhang, Pei Li, Shan Xi, Wei Guo, Yukang Shen, Zehui Xiong, Jiawen Kang, Dusit Niyato, Xiuquan Qiao, Yi Wu
2022 arXiv   pre-print
Finally, we discuss future research directions to realize the true vision of Metaverse with 6G-enabled edge AI.  ...  Then we summarize technical challenges that these architectures face in Metaverse and the existing solutions.  ...  In this paper, we survey the challenges, methods, and future research directions of the 6G-enabled edge AI architecture empowered by Metaverse.  ... 
arXiv:2204.06192v1 fatcat:cxd5g5vd75gnbowiece77aibea

Deep Learning in Cancer Diagnosis and Prognosis Prediction: A Minireview on Challenges, Recent Trends, and Future Directions

Ahsan Bin Tufail, Yong-Kui Ma, Mohammed K. A. Kaabar, Francisco Martínez, A. R. Junejo, Inam Ullah, Rahim Khan, Iman Yi Liao
2021 Computational and Mathematical Methods in Medicine  
Aims are to scrutinize the influence of DL systems using histopathology images, present a summary of state-of-the-art DL methods, and give directions to future researchers to refine the existing methods  ...  Deep learning (DL) is a branch of machine learning and artificial intelligence that has been applied to many areas in different domains such as health care and drug design.  ...  Section 5 presents the discussion covering limitations of the existing methods, perspectives, and some directions for future work.  ... 
doi:10.1155/2021/9025470 pmid:34754327 pmcid:PMC8572604 fatcat:wgpostjgsfeijazpyguobcrx4i

Emerging Trends in Federated Learning: From Model Fusion to Federated X Learning [article]

Shaoxiong Ji and Teemu Saravirta and Shirui Pan and Guodong Long and Anwar Walid
2021 arXiv   pre-print
This survey reviews the state of the art, challenges, and future directions.  ...  , and Bayesian methods.  ...  Besides, we point out challenges and outlook future directions in this specific category of research on federated learning.  ... 
arXiv:2102.12920v2 fatcat:5fcwfhxibbedbcbuzrfyqdedky

Active Federated Learning [article]

Jack Goetz, Kshitiz Malik, Duc Bui, Seungwhan Moon, Honglei Liu and Anuj Kumar
2019 arXiv   pre-print
To exploit this we propose Active Federated Learning, where in each round clients are selected not uniformly at random, but with a probability conditioned on the current model and the data on the client  ...  Federated Learning allows for population level models to be trained without centralizing client data by transmitting the global model to clients, calculating gradients locally, then averaging the gradients  ...  Adding privacy guarantees is an important challenge in AFL and is the subject of much future work.  ... 
arXiv:1909.12641v1 fatcat:rybnm46hs5d7zmprnv2gi3zfui

One-Shot Federated Learning [article]

Neel Guha, Ameet Talwalkar, Virginia Smith
2019 arXiv   pre-print
We discuss these methods and identify several promising directions of future work.  ...  We present one-shot federated learning, where a central server learns a global model over a network of federated devices in a single round of communication.  ...  Award, a Carnegie Bosch Institute Research Award, and the CONIX Research Center.  ... 
arXiv:1902.11175v2 fatcat:kjaehm6u2bddpbro2bbyvwbtoy

Federated Quantum Machine Learning

Samuel Yen-Chi Chen, Shinjae Yoo
2021 Entropy  
It demonstrates a promising future research direction for scaling and privacy aspects.  ...  One of the potential schemes to achieve this property is the federated learning (FL), which consists of several clients or local nodes learning on their own data and a central node to aggregate the models  ...  The implementation of these advanced protocols with quantum machine learning is an interesting direction for future work.  ... 
doi:10.3390/e23040460 pmid:33924721 fatcat:5qszfv4twvaztaytpvx677juwa

Federated Reconstruction: Partially Local Federated Learning [article]

Karan Singhal, Hakim Sidahmed, Zachary Garrett, Shanshan Wu, Keith Rush, Sushant Prakash
2022 arXiv   pre-print
Personalization methods in federated learning aim to balance the benefits of federated and local training for data availability, communication cost, and robustness to client heterogeneity.  ...  We introduce Federated Reconstruction, the first model-agnostic framework for partially local federated learning suitable for training and inference at scale.  ...  for their helpful comments and discussions.  ... 
arXiv:2102.03448v6 fatcat:shjujqe6rjcbvkrsovfo7ktm3u

Federated Mutual Learning [article]

Tao Shen, Jie Zhang, Xinkang Jia, Fengda Zhang, Gang Huang, Pan Zhou, Kun Kuang, Fei Wu, Chao Wu
2020 arXiv   pre-print
However, there are three types of heterogeneities in FL setting bringing about distinctive challenges to the canonical federated learning algorithm (FedAvg).  ...  scenes and tasks; In this work, we present a novel federated learning paradigm, named Federated Mutual Leaning (FML), dealing with the three heterogeneities.  ...  This feature may derive some research about adversarial training in federated learning in the future.  ... 
arXiv:2006.16765v3 fatcat:3kifsth6kng4zntkc3krp5sv7a

Federated Quantum Machine Learning [article]

Samuel Yen-Chi Chen, Shinjae Yoo
2021 arXiv   pre-print
It demonstrates a promising future research direction for scaling and privacy aspects.  ...  Our distributed federated learning scheme demonstrated almost the same level of trained model accuracies and yet significantly faster distributed training.  ...  The implementation of these advanced protocols with quantum machine learning is an interesting direction for future work. C.  ... 
arXiv:2103.12010v1 fatcat:x5eepz6uhbgfvctc2gcx7ul2ru

Vulnerabilities in Federated Learning

Nader Bouacida, Prasant Mohapatra
2021 IEEE Access  
We highlight the vulnerabilities sources, key attacks on FL, defenses, as well as their unique challenges, and discuss promising future research directions towards more robust FL.  ...  To date, the security of traditional machine learning systems has been widely examined. However, many open challenges and complex questions are still surrounding FL security.  ...  FEDERATED MULTI-TASK LEARNING Federated multi-task learning [116] - [119] handles statistical and system challenges of FL like high communication costs, stragglers, and fault tolerance.  ... 
doi:10.1109/access.2021.3075203 doaj:5e62c955db514036939a1c65011f46b8 fatcat:viv7tij6cffnlev4l52wggkxfe

Asynchronous Hierarchical Federated Learning [article]

Xing Wang, Yijun Wang
2022 arXiv   pre-print
Federated Learning is a rapidly growing area of research and with various benefits and industry applications.  ...  In addition, asynchronous federated learning schema is used to tolerate heterogeneity of the system and achieve fast convergence, i.e., the server aggregates the gradients from the workers weighted by  ...  Conclusions and Future Work In this paper, we propose asynchronous hierarchical federated learning.  ... 
arXiv:2206.00054v1 fatcat:otif2b4bubefjjgkp5ygtmkngy

Towards Verifiable Federated Learning [article]

Yanci Zhang, Han Yu
2022 arXiv   pre-print
Currently, there is no comprehensive survey on the field of verifiable federated learning, which is interdisciplinary in nature and can be challenging for researchers to enter into.  ...  Verifiable federated learning has become an emerging topic of research that has attracted significant interest from the academia and the industry alike.  ...  The field of verifiable federated learning is interdisciplinary as it requires expertise from machine learning, cryptography and game theory, etc.  ... 
arXiv:2202.08310v1 fatcat:ix5apesjpzaovcky3gs7s5keom
« Previous Showing results 1 — 15 out of 224,707 results